自适应模糊神经网络控制在锅炉过热汽温控制中的应用

常规的模糊控制系统不能自动地将专家知识经验转化为推理规则库,缺乏有效的方法来改进隶属度函数,而自适应神经模糊推理系统(ANFIS)将模糊逻辑和神经元相结合,采用反向传播算法和最小二乘法的混合算法来调整前提参数和结论参数,并能自动产生模糊规则.在此基础上提出了一种自适应模糊神经网络控制器,并将其应用于火电厂锅炉过热汽温控制中.结果表明:与常规的PID控制相比,该方法提高了锅炉汽温控制系统的动态稳定性和抗干扰性.     

Doubly-fed induction generator drive based WECS using fuzzy logic controller

The purpose of this paper is to improve the control performance of the variable speed, constant frequency doubly-fed induction generator in the wind turbine generation system by using fuzzy logic controllers. The control of the rotor-side converter is realized by stator flux oriented control, whereas the control of the grid-side converter is performed by a control strategy based on grid voltage orientation to maintain the DC-link voltage stability. An intelligent fuzzy inference system is proposed as an alternative of the conventional proportional and integral (PI) controller to overcome any disturbance, such as fast wind speed variation, short grid voltage fault, parameter variations and so on. Five fuzzy logic controllers are used in the rotor side converter (RSC) for maximum power point tracking (MPPT) algorithm, active and reactive power control loops, and another two fuzzy logic controllers for direct and quadratic rotor currents components control loops. The performances have been tested on 1.5 MW doubly-fed induction generator (DFIG) in a Matlab/Simulink software environment.     

直接转矩控制中基于模糊推理的相位补偿

基于数字信号处理器ＴＭＳ３２０Ｆ２４０给出了一个动态的模糊预测电流补偿的方法,针对感应电机提高了直接转矩控制的低速性能,引入了一种模糊控制方法来补偿ＰＷＭ信号中由死区和芯片延时引起的相位误差,根据电流的幅值与方向,结合瞬时电压,采用模糊推理对相位误差进行补偿,可以在一定程度上提高控制的性能,仿真与实验结果表明的这种方法是可行的。     

Resiliency oriented control of a smart microgrid with photovoltaic modules

The resiliency of a standalone microgrid is of considerable issue because the available regulation measures and capabilities are limited. Given this background, this paper presented a new mathematical model for a detailed photovoltaic (PV) module and the application of new control techniques for efficient energy extraction. The PV module employs a single-stage conversion method to integrate it with the utility grid. For extraction the maximum power from PV and integrate it to power grid, a three-phase voltage source converter is used. For obtaining the maximum power at a particular irradiance a maximum power point tracking (MPPT) scheme is used. The fuzzy logic control and adaptive network-based fuzzy inference system are proposed for direct current (DC) link voltage control. The proposed model and control scheme are validated through a comparison with the standard power-voltage and current–voltage charts for a PV module. Simulation results demonstrate that the system stability can be maintained with the power grid and in the island mode, in contrast with the MPPT.     

Assessment of a fuzzy logic based MRAS observer used in a photovoltaic array supplied AC drive

In this paper a fuzzy logic (FL) based model reference adaptive system (MRAS) speed observer for high performance AC drives is proposed. The error vector computation is made based on the rotor-flux derived from the reference and the adaptive model of the induction motor. The error signal is processed in the proposed fuzzy logic controller (FLC) for speed adaptation. The drive employs an indirect vector control scheme for achieving a good closed loop speed control. For powering the drive system, a standalone photovoltaic (PV) energy source is used. To extract the maximum power from the PV source, a constant voltage controller (CVC) is also proposed. The complete drive system is modeled in MATLAB/Simulink and the performance is analyzed for different operating conditions.     

基于SVPWM的异步风力发电机直接转矩控制方法的研究

提出了一种改进的异步风力发电机直接转矩控制方法,此方法不仅简单,而且性能优于传统的滞环比较器控制方式。利用转矩模糊控制器和磁链控制器代替传统的滞环比较器,通过Matlab/Simulink仿真表明,基于空间矢量脉宽调制的直接转矩改进方法不仅改善了异步发电机稳态转矩脉动大的问题,而且减小了电机启动电流,还大大提高了整个控制系统的性能。     

水轮发电机组的直接自适应模糊控制

提出了一种新颖的直接自适应模糊控制方法。基于筒化了的T－S（Takagi-Sugeno）模糊推理规则,采用神经网络权值的联想式学习修正方法,对T－S模糊推理规则进行在线修正,给出了盯应的神经网络实现结构,从而实现了不需要建立受控对象模型的直接自适应模糊控制。对一混流式水轮机组的仿真控制实验结果证明了所提出方法具有设计简单、鲁棒性强的优点,能适应水轮机组在不同工况下的控制要求。     

A fuzzy logic based power system stabilizer with learning ability

A fuzzy logic-based power system stabilizer (PSS) with learning ability is proposed in this paper. The proposed PSS employs a multilayer adaptive network. The network is trained directly from the input and the output of the generating unit. The algorithm combines the advantages of artificial neural networks (ANNs) and fuzzy logic control (FLC) schemes. Studies show that the proposed adaptive network-based fuzzy logic PSS (ANF PSS) can provide good damping of power systems over a wide range of operating conditions and improve the dynamic performance of the power system     

Observer-based type-2 fuzzy approach for robust control and energy management strategy of hybrid energy storage systems

In this paper, an observer-based type-2 fuzzy method is proposed for control and energy management strategy (EMS) of the hybrid energy storage system (HESS) which can be composed of the fuel cell (FC), battery (BA), and supercapacitor (SC). The objective and main contribution of the suggested strategy is to provide: 1) Appropriate tracking performance of power sources by an observer-based control method in the presence of noise and signal ripples. 2) An observer-based composite adaptive type-2 fuzzy (OCAT2F) to approximate the voltage of power sources. 3) A dynamical model of DC-bus to guarantee the stability of closed-loop system. 4) An intelligent EMS. To have a high-power supply, the proposed EMS includes two parts; a type-2 fuzzy logic control rule table (T2FLCRT), and an observer-based robust adaptive fuzzy type-2 fuzzy (ORAT2F). Furthermore, stability analyses of the closed-loop system are provided by the input-output linearization (I-OL) approach and based on the Lyapunov theorem. The simulation results of the proposed control scheme under MATLAB/Simulink indicate that the suggested strategy can provide a suitable control performance, and stability of the whole system is achieved.     

基于SSA-PSO-ANFIS的短期风速预测研究

针对风速具有强非线性的特点,提出一种奇异谱分析和改进粒子群优化自适应模糊推理系统的短期风速预测模型。该方法采用奇异谱分析将原始序列分解为趋势和谐波分量,对各分量分别建立模糊神经网络模型,最后将各分量预测结果叠加得到预测风速值。为提高预测精度,改用改进粒子群算法对自适应模糊推理系统的隶属度函数进行优化。以河北某风电场实测数据进行仿真并与传统的神经网络对比分析,结果表明将风速重构后分别预测再叠加降低了原始问题的复杂度,同时提高了预测精度,在不同时间间隔的风速序列预测中该模型显著降低了多步实时预测中的误差。     

Optimization of fuzzy-based MPPT controller via metaheuristic techniques for stand-alone PV systems

Due to the alteration of power-voltage characteristics of solar module output under multiple environmental conditions such as solar irradiation and ambient temperature, these systems hardly function at maximum power point (MPP). However, maximum power point tracking (MPPT) plays a significant role in their efficiency. On the other hand, solar module characteristics are extremely nonlinear and their slope on either side of MPP is asymmetric. Thus using a nonlinear control method which has the potential of adapting the operating point of the system to MPP seems useful. This has motivated authors to present MPPT method which maximizes PV's output power by tracking MPP continuously. In the present study, a fuzzy logic controller (FLC) is presented for MPPT in photovoltaic systems. Four optimization algorithms are presented in this paper for optimizing fuzzy membership functions (MFs) and generating proper duty cycle for MPPT. The presented algorithms include: Teaching Learning Based Optimization (TLBO), Firefly Algorithm (FFA), Biogeography based optimization (BBO), and Particle Swarm Optimization (PSO), which are all described and simulated. Finally, to validate performance of the proposed optimized FLC, it is compared with other algorithms such as symmetrical fuzzy logic controller (SFLC) and conventional Perturbation and Observation (P&O). According to the simulation results, P&O algorithm shows significant oscillations, energy loss, and in some cases, it cannot obtain MPP. Simulation results also indicate that TLBO and FFA based asymmetric fuzzy MFs not only increase MPPT convergence speed but also enhance tracking accuracy in comparison with symmetric fuzzy MFs and asymmetric fuzzy MFs based on BBO and PSO.     

Maximum power point tracking using adaptive fuzzy logic control for grid-connected photovoltaic system

This paper proposes a method of maximum power point tracking using adaptive fuzzy logic control for grid-connected photovoltaic systems. The system is composed of a boost converter and a single-phase inverter connected to a utility grid. The maximum power point tracking control is based on adaptive fuzzy logic to control a switch of a boost converter. Adaptive fuzzy logic controllers provide attractive features such as fast response, good performance. In addition, adaptive fuzzy logic controllers can also change the fuzzy parameter for improving the control system. The single phase inverter uses predictive current control which provides current with sinusoidal waveform. Therefore, the system is able to deliver energy with low harmonics and high power factor. Both conventional fuzzy logic controller and adaptive fuzzy logic controller are simulated and implemented to evaluate performance. Simulation and experimental results are provided for both controllers under the same atmospheric condition. From the simulation and experimental results, the adaptive fuzzy logic controller can deliver more power than the conventional fuzzy logic controller.     

Adaptive fuzzy gain scheduling PID controller for maximum power point tracking of photovoltaic system

This paper proposes a methodology of designing a Maximum Power Point Tracking (MPPT) controller for photovoltaic systems (PV) using a Fuzzy Gain Scheduling of Proportional-Integral-Derivative (PID) type controller (FGS-PID) with adaptation of scaling factors (SF) for the input signals of FGS. The proposed adaptive FGS-PID method is based on a two-level control system architecture, which combines the advantages of fuzzy logic and conventional PID control. The initial values of the PID's gains are determined by the Ziegler–Nichols tuning method. During transient and steady states, the PID's gains are adapted by the FGS-PID to damp out the transient oscillations, to reduce settling time and to guarantee system stability and accuracy. Also, the conditioned input signals of the FGS-PID are tuned dynamically by gain factors which are based on fuzzy logic system (FLS). The FLS is characterized by a set of fuzzy rules which are fuzzy conditional statements expressing the relationship between inputs (error and change of error) and outputs. This approach creates an adaptive MPPT controller and achieves better overall system performance. The simulation results demonstrate the effectiveness of the proposed adaptive FGS-PID and show that this approach can achieve a good maximum power operation under any conditions such as different levels of solar radiation and PV cell temperature for varying PV sources. Compared to conventional methods (PID, perturb and observe method P&O), this method shows a considerable high tracking performance.     

Fuzzy logic application for intelligent control of a variable speeddrive

The slip power recovery configuration is an attractive scheme of variable speed drive, with high efficiency and low power converter rating; however, high performance control has been difficult. In this paper, novel applications of fuzzy logic for the intelligent control of a slip power recovery system are presented. A direct fuzzy logic controller and an adaptive fuzzy controller, based on model reference adaptive control, are developed and simulated for the doubly-excited induction machine and power converter system. Compared with field orientation control, the intelligent control of a complex slip power recovery system reduces costs and enhances robust and desired performance     

Intelligent fuzzy weighted input estimation method applied to inverse heat conduction problems

The innovative intelligent fuzzy weighted input estimation method which efficiently and robustly estimates the unknown time-varying heat flux in real-time is presented in this paper. The algorithm includes the Kalman Filter (KF) and the recursive least square estimator (RLSE), which is weighted by the fuzzy weighting factor proposed based on the fuzzy logic inference system. To directly synthesize the Kalman filter with the estimator, this work presents an efficient robust forgetting zone, which is capable of providing a reasonable compromise between the tracking capability and the flexibility against noises. The capability of this inverse method are demonstrated in one- and two-dimensional time-varying estimation cases and the proposed algorithm is compared by alternating between the constant and adaptive weighting factors. The results show that this method has the properties of faster convergence in the initial response, better target tracking capability and more effective noise reduction.     

基于模糊神经网络的发动机故障诊断专家系统的研究

根据发动机的组成结构、功能原理及维修专家的实际经验，提出了一种基于模糊神经网络的故障诊断方法，将模糊逻辑和神经网络与传统的专家系统结合起来，开发出发动机故障诊断专家系统软件。该系统具有推理过程简单、快捷和准确等优点。     

Neural network-based self-organizing fuzzy controller for transientstability of multimachine power systems

An efficient self-organizing neural fuzzy controller (SONFC) is designed to improve the transient stability of multimachine power systems. First, an artificial neural network (ANN)-based model is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the ANN model. With the excellent learning capability inherent in the ANN, the traditional heuristic fuzzy control rules and input/output fuzzy membership functions can be optimally tuned from training examples by the backpropagation learning algorithm. Considerable rule-matching times of the inference engine in the traditional fuzzy system can be saved. To illustrate the performance and usefulness of the SONFC, comparative studies with a bang-bang controller are performed on the 34-generator Taipower system with rather encouraging results     

THD reduction with reactive power compensation for fuzzy logic DVR based solar PV grid connected system

Dynamic voltage restorer (DVR) is used to protect sensitive loads from voltage disturbances of the distribution generation (DG) system. In this paper, a new control approach for the 200 kW solar photovoltaic grid connected system with perturb and observe maximum power point tracking (MPPT) technique is implemented. Power quality improvement with comparison is conducted during fault with proportional integral (PI) and artificial intelligence-based fuzzy logic controlled DVR. MPPT tracks the actual variable DC link voltage while deriving the maximum power from a photovoltaic array and maintains DC link voltage constant by changing modulation index of the converter. Simulation results during fault show that the fuzzy logic based DVR scheme demonstrates simultaneous exchange of active and reactive power with less total harmonic distortion (THD) present in voltage source converter (VSC) current and grid current with fast tracking of optimum operating point at unity power factor. Standards (IEEE-519/1547), stipulates that the current with THD greater than 5% cannot be injected into the grid by any distributed generation source. Simulation results and validations of MPPT technique and operation of fuzzy logic controlled DVR demonstrate the effectiveness of the proposed control schemes.     

Power quality improvement using fuzzy logic controller for five-level shunt active power filter under distorted voltage conditions

In this paper, a five-level inverter is used as a shunt active power filter (APF), taking advantages of the multilevel inverter such as low harmonic distortion and reduced switching losses. It is used to compensate reactive power and eliminate harmonics drawn from a thyristor rectifier feeding an inductive load (RL) under distorted voltage conditions. The APF control strategy is based on the use of self-tuning filters (STF) for reference current generation and a fuzzy logic current controller. The use of STF instead of classical extraction filters allows extracting directly the voltage and current fundamental components in the α-β axis without phase locked loop (PLL). The MATLAB fuzzy logic toolbox is used for implementing the fuzzy logic control algorithm. The obtained results show that the proposed shunt APF controller has produced a sinusoidal supply current with low harmonic distortion and in phase with the line voltage.     

Modeling of a 5-cell direct methanol fuel cell using adaptive-network-based fuzzy inference systems

The methanol concentrations, temperature and current were considered as inputs, the cell voltage was taken as output, and the performance of a direct methanol fuel cell (DMFC) was modeled by adaptive-network-based fuzzy inference systems (ANFIS). The artificial neural network (ANN) and polynomial-based models were selected to be compared with the ANFIS in respect of quality and accuracy. Based on the ANFIS model obtained, the characteristics of the DMFC were studied. The results show that temperature and methanol concentration greatly affect the performance of the DMFC. Within a restricted current range, the methanol concentration does not greatly affect the stack voltage. In order to obtain higher fuel utilization efficiency, the methanol concentrations and temperatures should be adjusted according to the load on the system.